Skip to content
Heist/ feed
Back to feed
Low

vLLM: Permissive default CORS origins allow cross-origin requests to the vLLM HTTP server

Type: advisorySources: Official CVE List

vLLM is an inference and serving engine for large language models. Prior to 0.32.0, the OpenAI-compatible server configures Starlette CORSMiddleware with allowed_origins set to a wildcard by default. A malicious web page can use a victim's browser to reach an unauthenticated vLLM server on localhost, an internal network, or a VPN, call endpoints including GET /v1/models and POST /v1/chat/completions, consume GPU resources, and read responses. Cookie-based cross-site request forgery does not apply because credentials are disabled by default, and deployments requiring bearer authentication are exposed only when the caller already has a usable token. This issue is fixed in version 0.32.0.

Products
vllm
Affected versions
Not specified
Fixed versions
Not specified
CVEs
CVE-2026-115917
Confirmed fixed CVEs
Not specified
Updated in this feed
30 Oct 2026, 15:07 UTC · Revision 1

Source evidence

vLLM: Permissive default CORS origins allow cross-origin requests to the vLLM HTTP server

core-cve · Original source

Published 26 Oct 2026, 17:20 UTC

vLLM is an inference and serving engine for large language models. Prior to 0.32.0, the OpenAI-compatible server configures Starlette CORSMiddleware with allowed_origins set to a wildcard by default. A malicious web page can use a victim's browser to reach an unauthenticated vLLM server on localhost, an internal network, or a VPN, call endpoints including GET /v1/models and POST /v1/chat/completions, consume GPU resources, and read responses. Cookie-based cross-site request forgery does not apply because credentials are disabled by default, and deployments requiring bearer authentication are exposed only when the caller already has a usable token. This issue is fixed in version 0.32.0.

cve:CVE-2026-115917

vllm

Fixed versions: Not specified

Complete source record
{
  "id": "2446587b823b036fa6e8b8e11faa57fab6ce2f2edc0244b2900d484ce9ae0c1f",
  "url": "https://www.cve.org/CVERecord?id=CVE-2026-115917",
  "method": "structured",
  "payload": {
    "kind": "advisory",
    "title": "vLLM: Permissive default CORS origins allow cross-origin requests to the vLLM HTTP server",
    "summary": "vLLM is an inference and serving engine for large language models. Prior to 0.32.0, the OpenAI-compatible server configures Starlette CORSMiddleware with allowed_origins set to a wildcard by default. A malicious web page can use a victim's browser to reach an unauthenticated vLLM server on localhost, an internal network, or a VPN, call endpoints including GET /v1/models and POST /v1/chat/completions, consume GPU resources, and read responses. Cookie-based cross-site request forgery does not apply because credentials are disabled by default, and deployments requiring bearer authentication are exposed only when the caller already has a usable token. This issue is fixed in version 0.32.0.",
    "evidence": "cve:CVE-2026-115917",
    "products": [
      {
        "name": {
          "value": "vllm",
          "evidence": "/containers/cna/affected/0/product"
        },
        "prerequisites": [],
        "fixed_versions": [],
        "affected_versions": []
      }
    ],
    "severity": "low",
    "structured": {
      "id": "CVE-2026-115917",
      "aliases": [
        "CVE-2026-115917"
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "scope": "CHANGED",
            "version": "3.1",
            "baseScore": 3.4,
            "attackVector": "NETWORK",
            "baseSeverity": "LOW",
            "vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:C/C:L/I:N/A:N",
            "integrityImpact": "NONE",
            "userInteraction": "REQUIRED",
            "attackComplexity": "HIGH",
            "availabilityImpact": "NONE",
            "privilegesRequired": "NONE",
            "confidentialityImpact": "LOW"
          }
        }
      ],
      "affected": [
        {
          "vendor": "vllm-project",
          "product": "vllm",
          "versions": [
            {
              "status": "affected",
              "version": "< 0.32.0"
            }
          ]
        }
      ],
      "modified": "2026-10-26T17:20:09.065Z",
      "provider": "cve",
      "references": [
        "https://github.com/vllm-project/vllm/security/advisories/GHSA-vvpg-rrww-wpmh",
        "https://github.com/vllm-project/vllm/pull/61009",
        "https://github.com/vllm-project/vllm/commit/fcae5c98870ff2c20659731dce7ba3a3ff0d48aa",
        "https://github.com/vllm-project/vllm/releases/tag/v0.32.0"
      ],
      "provider_metadata": {
        "cna": {
          "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
          "shortName": "GitHub_M",
          "dateUpdated": "2026-10-26T17:20:09.065Z"
        }
      }
    },
    "related_cves": [
      {
        "value": "CVE-2026-115917",
        "evidence": "/cveMetadata/cveId"
      }
    ],
    "security_relevant": true,
    "severity_evidence": "/containers/cna/metrics"
  },
  "source_id": "core-cve",
  "document_id": 324477,
  "published_at": "2026-10-26T17:20:09.065+00:00"
}